cs.RO（2025-05-19）

📊 共 23 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (15 🔗4) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (15 篇)

#题目一句话要点标签🔗⭐
1 TD-GRPC: Temporal Difference Learning with Group Relative Policy Constraint for Humanoid Locomotion 提出TD-GRPC，结合时序差分学习与群组相对策略约束，提升人形机器人运动控制的稳定性和鲁棒性。 humanoid humanoid robot humanoid control
2 Dribble Master: Learning Agile Humanoid Dribbling Through Legged Locomotion 提出基于强化学习的两阶段课程学习框架，实现敏捷人形机器人足球运球 legged locomotion humanoid humanoid robot ✅
3 Disentangling Coordiante Frames for Task Specific Motion Retargeting in Teleoperation using Shared Control and VR Controllers 提出解耦坐标系的遥操作运动重定向方法，提升VR控制下的任务效率 teleoperation shared control motion retargeting
4 Dynamic Bipedal MPC with Foot-level Obstacle Avoidance and Adjustable Step Timing 提出一种足端避障和步态时序调整的动态双足机器人MPC控制框架 bipedal biped MPC
5 TeleOpBench: A Simulator-Centric Benchmark for Dual-Arm Dexterous Teleoperation 提出TeleOpBench以解决双臂灵巧遥操作的基准测试问题 manipulation dexterous hand bi-manual ✅
6 Composing Dextrous Grasping and In-hand Manipulation via Scoring with a Reinforcement Learning Critic 利用强化学习Critic评分，实现灵巧抓取与手内操作的组合 manipulation in-hand manipulation reinforcement learning
7 Granular Loco-Manipulation: Repositioning Rocks Through Strategic Sand Avalanche DiffusiveGRAIN：通过策略性沙土崩塌实现移动机器人对岩石的精细操控 legged robot locomotion manipulation
8 The Robot of Theseus: A modular robotic testbed for legged locomotion 提出模块化四足机器人TROT，用于生物力学研究和步态控制策略开发 quadruped legged robot legged locomotion
9 Adaptive Diffusion Constrained Sampling for Bimanual Robot Manipulation 提出自适应扩散约束采样方法，解决双臂机器人操作中的复杂约束规划问题 manipulation bi-manual dual-arm
10 DreamGen: Unlocking Generalization in Robot Learning through Video World Models DreamGen：通过视频世界模型解锁机器人学习的泛化能力 humanoid humanoid robot teleoperation ✅
11 Approximating Global Contact-Implicit MPC via Sampling and Local Complementarity 提出基于采样和局部互补的全局接触隐式MPC，用于灵巧操作 manipulation dexterous manipulation MPC
12 SafeMove-RL: A Certifiable Reinforcement Learning Framework for Dynamic Motion Constraints in Trajectory Planning SafeMove-RL：基于动态安全裕度的强化学习轨迹规划框架 trajectory optimization motion planning reinforcement learning
13 GraspMolmo: Generalizable Task-Oriented Grasping via Large-Scale Synthetic Data Generation GraspMolmo：基于大规模合成数据的通用任务导向抓取模型 manipulation bi-manual open-vocabulary ✅
14 Practice Makes Perfect: A Study of Digital Twin Technology for Assembly and Problem-solving using Lunar Surface Telerobotics 利用数字孪生技术提升月球表面遥操作机器人装配与问题解决能力 manipulation teleoperation
15 Audio-Visual Contact Classification for Tree Structures in Agriculture 提出多模态分类框架以解决农业树结构接触识别问题 manipulation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
16 Policy Contrastive Decoding for Robotic Foundation Models 提出策略对比解码(PCD)方法，提升机器人通用策略在真实环境中的泛化能力。 foundation model Octo OpenVLA ✅
17 SayCoNav: Utilizing Large Language Models for Adaptive Collaboration in Decentralized Multi-Robot Navigation SayCoNav：利用大型语言模型实现去中心化多机器人导航中的自适应协作 large language model
18 A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics 综述：具身智能大模型机器人物理风险控制方法 foundation model
19 Seeing, Saying, Solving: An LLM-to-TL Framework for Cooperative Robots 提出LLM-to-TL框架，解决异构机器人团队协作中的冲突问题 large language model
20 Hybrid Voting-Based Task Assignment in Modular Construction Scenarios 提出HVBTA框架，解决模块化建造中多智能体任务分配与冲突避免问题 large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
21 OPA-Pack: Object-Property-Aware Robotic Bin Packing 提出OPA-Pack框架以解决机器人装箱中的物体属性问题 height map chain-of-thought
22 Risk-Averse Traversal of Graphs with Stochastic and Correlated Edge Costs for Safe Global Planetary Mobility 提出风险规避的图遍历算法，用于随机成本下安全行星移动 traversability

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
23 A Practical Guide for Incorporating Symmetry in Diffusion Policy 提出一种将对称性融入扩散策略的实用指南，提升采样效率和泛化能力。 policy learning diffusion policy

⬅️ 返回 cs.RO 首页 · 🏠 返回主页